VideoAgentTrek: Computer-Use Pretraining from Unlabeled Videos

Dunjie Lu, Yiheng Xu, Junli Wang, Haoyuan Wu, Xinyuan Wang, Zekun Wang, Junlin Yang, Hongjin SU, Jixuan Chen, Junda Chen, Yuchen Mao, Junyang Lin, Binyuan Hui, Tao Yu

Keywords: VideoAgentTrek

TL;DR: VideoAgentTrek automatically mines GUI action trajectories from unlabeled screen-recorded videos via inverse dynamics, enabling scalable computer-use agent pretraining with 70% relative improvement on OSWorld-Verified.

Abstract: Training computer-use agents requires massive amounts of GUI interaction data, but manually annotating action trajectories at scale is prohibitively expensive. We present VideoAgentTrek, a scalable pipeline that automatically mines training data from publicly available screen-recorded videos, eliminating the need for manual annotation. Our approach addresses a key challenge: raw videos contain implicit demonstrations but lack explicit action labels. To solve this, we develop Video2Action, an inverse dynamics module (IDM) with two components: (1) a video grounding model that detects and localizes GUI actions with precise temporal boundaries, and (2) an action-content recognizer that extracts structured parameters like click coordinates and typed text. Applied to 39,000 YouTube tutorial videos, our pipeline generates 1.52 million interaction steps. We leverage this data through continued pretraining followed by supervised fine-tuning. On OSWorld-Verified, our approach improves task success rates from 9.3% (SFT-only baseline) to 15.8%, a 70% relative improvement. On AgentNetBench, step accuracy increases from 64.1% to 69.3%. Our results demonstrate that passive internet videos can be transformed into high-quality supervision for computer-use agents, providing a scalable alternative to expensive manual annotation.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 4108